+ Reply to Thread
Results 1 to 2 of 2

Thread: ANOVA und Cohens d`?

  1. #1
    Points: 4, Level: 1
    Level completed: 7%, Points required for next Level: 46

    Thanked 0 Times in 0 Posts

    ANOVA und Cohens d`?

    Hi there!

    So, i did a psychological study where i tried to manipulate flow. In that study every subject had to play a racing game 6 times and after each round he or she had to do a questionaire for the measurement of flow. Every subject played 3 different Tracks 2 times. There were 3 types of manipulation. So every subject played 3 times with and 3 times without manipulation. To prevent training and other effects i balanced the whole thing with two interlaced latin squares to the effect that every manipulation existed with every track on every position in the sequence. For that 18 subjects would have been enough but i did 36 to be on the safe side.

    Then i did a ANOVA on the data with SPSS.
    without manipulation: 55,4722 (SD=7,33123) n=108
    manipulation 1: 41,1944 (SD=8,38645) n=36
    manipulation 2: 51,3333 (SD=7,81574) n=36
    manipulation 3: 46,4722 (SD=6,95490) n=36

    Now im not sure if i can calculate a Cohens d like with T-tests because i cant decide if the samples are connected or not...

    Can somebody help me with this? Can i even calculate a effectsize here?



  2. #2
    Cookie Scientist
    Points: 13,806, Level: 76
    Level completed: 39%, Points required for next Level: 244
    Jake's Avatar
    Austin, TX
    Thanked 584 Times in 438 Posts

    Re: ANOVA und Cohens d`?

    I've written a blog post on Cohen's-d-type effect sizes for general ANOVA designs which you might find useful: http://jakewestfall.org/blog/index.p...bject-designs/
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

+ Reply to Thread


Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats